Campus del Baix Llobregat
 
Projectes oferts

Projectes matriculats

Tribunals i dates de lectura

Projectes llegits
(2019-2)

DG ENG AERO/SIS TEL

DG ENG AERO/TELEMÀT

DG ENG SISTE/TELEMÀT

ENG TELEC 2NCICLE 01

ET AERO/ETT SIST 05

ET AERONÀUTICA 03

ETT SIST/ ET AERO 05

ETT SIST TELEC 00

ETT SIST TELEC 91

ETT TELEMÀTICA 00

GR ENG AERONAVEGACIÓ

GR ENG AEROPORTS

GR ENG SIS TELECOMUN

GR ENG SIST AEROESP

GR ENG TELEMÀTICA

MU AEROSPACE S&T 09

MU DRONS

MU MASTEAM 2009

MU MASTEAM 2015

Cerca projectes

Calendari TFG de dipòsit i lectura

Documentació

Web UPC


 

Projecte llegit

Títol: Time to land prediction based on machine learning models

Estudiants que han llegit aquest projecte:

Director: BARRADO MUXÍ, Cristina

Departament: DAC

Títol: Time to land prediction based on machine learning models

Data inici oferta: 24-01-2020     Data finalització oferta: 24-09-2020


Estudis d'assignació del projecte:
    GR ENG SIST AEROESP
Tipus: Coordinat    Títol: Time to land prediction in Barcelona-El Prats airport based on machine learning classification models
 
Lloc de realització: EETAC
 
Paraules clau:
Machine learning, Airspace, Prediction, ATM
 
Descripció del contingut i pla d'activitats:
This project aims at designing a tool based on machine learning models capable of predicting the time of flight of an aircraft given the interactions with ATC. To do so, several data will be obtained from Flightradar24.com thanks to the ADS-B antenna installed at the roof of the university which is located at about 7 km westbound from Barcelona airport.

There is not a specific criterion other than safety for ATC to give vector. Nowadays, they depend on a “human factor” which is neither deterministic nor reliable. Machine learning will be the tool to extract a model capable of predicting those vectors in a consistent way. This model may be influenced by several factors such as: A/C type, weather, airline, speed, position, time of day, etc. It will also be fundamental to adjust the key parameters of the different regression models by training them. The used technique will consist on splitting the dataset into two parts, the first one as previously stated will be used to deduct the patterns and the second one will be used to check if the model is working as expected. The programming language to be used is Python since it has different libraries available such as SciKit-Learn or TensorFlow.

The benefits of giving vectors and shortcuts are: the reduction of the flight time thus reducing CO2 emissions, the possibility of compensating delays and the possibility of increasing the demand among others. On the other hand, the main drawbacks are that situational awareness is lost and although it may seem paradoxical if flight plan changes are not predicted, too many planes may be entering a certain sector during a dense traffic hour (compared with EURCONTROL’s daily prediction) and it may be impossible for controllers to sustain the demand, converting in that way a benefit into a problem.
 
Overview (resum en anglès):
The aim of the present Bachelor Final Project is to evaluate different machine learning (ML) models to predict the time any aircraft would take to land at Josep Tarradellas Barcelona-El Prat Airport.

To get a better picture of what ML really is and how it can be used in the air traffic management (ATM) field, a brief introduction of the different types of learning apart from viewing the areas of influence of this type of algorithms in some projects driven by the European R&D ATM program SESAR JU such as improving traffic predictability, enhancing the passenger flow in airports and improving airport operations’ performance.

To achieve the goal of the project, raw ADS-B messages sent by nearby aircraft of the airport have been used as the main source of information from which various ML algorithms have been fed with. Part of the data extracted from those messages like coordinates, altitudes, etc. have been used directly after being correspondingly processed and other type of information like the wake turbulence category (WTC), the landing runway and the meteorology have been obtained from indirect deduction from other fields of ADS-B messages and by using various databases.

Regarding the conclusions obtained at the end of this project, the best model found to predict the time any aircraft attempting to land at Josep Tarradellas Barcelona-El Prat Airport would need to do so is the RandomForestRegressor, being a supervised learning type of ML and as its name suggests, a regression-based model. Apart from being the most precise and accurate model, it is also the one with the most reasonable fit and score time, being key parameters when talking about a hypothetical actual implementation.

Finally, so as not to not discard any options for improvement, it is probable that better solutions can be achieved with the use of higher computational power due to the amount of calculations needed for some parts of the project.


Data de generació 26/01/2021